Structurally Observable Distributed Networks of Agents under Cost and Robustness Constraints

TL;DR

This paper introduces a polynomial time algorithm for designing cost-efficient, robust, structurally observable networks of agents, ensuring state inference with minimal probes even under multiple agent failures.

Contribution

It presents a novel polynomial time method for constructing minimally costly, structurally observable networks resilient to agent failures, advancing network design under robustness constraints.

Findings

Algorithm guarantees minimal cost network design.

Ensures observability despite up to k agent failures.

Applicable to sensor networks and robotic formations.

Abstract

In many problems, agents cooperate locally so that a leader or fusion center can infer the state of every agent from probing the state of only a small number of agents. Versions of this problem arise when a fusion center reconstructs an extended physical field by accessing the state of just a few of the sensors measuring the field, or a leader monitors the formation of a team of robots. Given a link cost, the paper presents a polynomial time algorithm to design a minimum cost coordinated network dynamics followed by the agents, under an observability constraint. The problem is placed in the context of structural observability and solved even when up to k agents in the coordinated network dynamics fail.